# ThinkStack MCP for AI Agents AI Agent Connect

> ThinkStack MCP lets you manage your entire chatbot fleet from your AI client. You can add knowledge sources like URLs or docs, send live queries to test responses, and audit conversation histories. It's the direct way to configure your AI's brain without leaving your workspace.

## Overview
- **Category:** productivity
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_jo2J6ijcE54rcC38l6SZTWj5QehkoD6Oykrxzd7S/ai-agent-connect
- **Tags:** thinkstack, chatbot-api, ai-manage, bot-actions, knowledge-base-sync, conversational-ai, chat-query-tools, customer-experience, mcp

## Description

ThinkStack gives you a direct line to your chatbot infrastructure. Instead of jumping between different dashboards to tweak your AI's knowledge or check how it's performing, you can do it all from your primary AI client. You can feed it new data by adding URLs or documents to specific bots, and then immediately test how those new facts influence the AI's answers. It takes the friction out of maintaining a production-ready chatbot because you can see the full conversation history and audit how your bots are interacting with real users. If you're looking for a central hub to oversee your conversational AI setup, this Connector is a great way to keep everything organized within the Vinkius catalog. You can even manage your webhook actions to make sure your bots are actually doing the work they're supposed to do. It's about having your entire chatbot operations under one roof where you can see the data and make changes in real time.

## Tools

### add_source
Add a new URL or document to a chatbot's knowledge base so it can be crawled and indexed.

### delete_source
Remove an outdated or incorrect knowledge source from a specific chatbot's data pool.

### get_bot
Fetch the specific details and configuration for a single chatbot in your account.

### get_conversation
Pull the full details and message history for a specific chat session.

### check_thinkstack_status
Verify that your connection to the ThinkStack API is active and working correctly.

### list_actions
See all the configured REST API actions that your chatbots are currently set up to trigger.

### list_bots
Get a complete list of every chatbot you have created in your ThinkStack account.

### list_conversations
Browse through all the chat sessions your bots have handled.

### list_sources
View all the URLs and documents currently serving as knowledge sources for your bots.

### send_query
Send a direct message to a chatbot and get a real-time response to test its behavior.

## Prompt Examples

**Prompt:** 
```
Show me all the bots I have and their current sources.
```

**Response:** 
```
### Your ThinkStack Bot Fleet

| Bot Name | Sources | Status |
| :--- | :--- | :--- |
| **Support Bot** | 24 Sources | Active |
| **Sales Assistant** | 8 Sources | Active |
| **Onboarding Guide** | 12 Sources | Active |

Would you like to see the specific URLs for any of these bots?
```

**Prompt:** 
```
Add this URL to my Support Bot: https://example.com/policy
```

**Response:** 
```
✅ **Source Added Successfully**

I've added `https://example.com/policy` to the **Support Bot**. ThinkStack is now crawling the page and will update the knowledge base within a few minutes. 

Would you like to test a query on this new policy now?
```

**Prompt:** 
```
Ask the Sales bot if we offer a 20% discount for annual plans.
```

**Response:** 
```
**Sales Assistant Response:**

"Yes, we currently offer a 20% discount for all annual plan subscribers. This includes premium features like advanced analytics and priority support."

**Status:** 
- **Bot:** Sales Assistant
- **Confidence:** High
- **Source:** Knowledge Base (Pricing Docs)
```

## Capabilities

### Add knowledge sources
Inject URLs or documents into your chatbots to update their training data.

### Query chatbots live
Send a message to a specific bot and see its response instantly.

### Audit conversation history
Review past chat sessions to see how users are interacting with your AI.

### Manage bot configurations
View and edit the settings for all the chatbots in your account.

### Sync webhook actions
Check the REST API actions your bots are configured to perform.

## Use Cases

### Updating a support bot
A support lead realizes the refund policy changed. They ask the agent to use add_source to add the new policy URL to the Support Bot.

### Testing a new sales bot
A product manager wants to see if the Sales Bot knows the new pricing. They use send_query to ask about the Enterprise Plan.

### Cleaning up old data
A developer notices a bot is giving outdated info. They use delete_source to remove a dead link from the knowledge base.

### Reviewing customer issues
A team lead wants to see why users are getting frustrated. They use list_conversations to find the most recent failed chats.

## Benefits

- No more tab-switching: Use list_bots and list_sources to see your entire setup in one place instead of logging into multiple dashboards.
- Faster knowledge updates: Use add_source to instantly feed new docs to your bots without manual uploads.
- Better quality control: Use send_query to test how a bot handles specific questions before you let customers see it.
- Easier auditing: Use list_conversations and get_conversation to spot where your bots are failing and fix the knowledge base.
- Simplified action management: Use list_actions to keep track of every webhook and API call your bots are making.

## How It Works

The bottom line is you get a unified control panel for your conversational AI fleet directly inside your AI client.

1. Retrieve your API key from the ThinkStack dashboard.
2. Connect this Connector to your AI client using that key.
3. Manage your bots and knowledge bases using natural language commands.

## Frequently Asked Questions

**Can I use ThinkStack MCP to manage multiple bots at once?**
Yes, you can list and manage every chatbot in your account from one place. This makes it easy to oversee a large fleet of bots without switching tabs.

**How do I add new documents to my chatbot's knowledge?**
You can simply tell your AI client to add a new source. It will handle the URL or document upload and start the crawling process for you.

**Can I see what my customers are saying to the bots?**
Yes, you can pull up full conversation histories. This allows you to review user interactions and identify where your bots might need better information.

**Does this Connector help with webhook actions?**
Yes, it lets you view all the configured REST API actions your bots are set up to trigger. This is helpful for verifying that your bots are correctly connected to your other tools.

**Is it easy to test bot responses before going live?**
Absolutely. You can send live queries to any bot in your account to see exactly how it responds before you deploy it to your customers.

**How do I know if my ThinkStack connection is working?**
You can check the API connectivity status at any time. This ensures that your AI client is always synced with your chatbot infrastructure.

**How do I query my chatbot via AI agent?**
Use the `send_query` tool with the bot ID and your message. The chatbot responds based on its trained knowledge base.

**Can I manage knowledge sources programmatically?**
Yes. Use `add_source` to add new URLs, `list_sources` to browse, and `delete_source` to remove outdated sources from any chatbot.

**How do I review chat conversations?**
Use `list_conversations` to see all chats for a bot, then `get_conversation` to read the full message history of any specific session.